Sufficient conditions on fuzzy logic controllers as universal approximators

被引:3
作者
Chen, WT [1 ]
机构
[1] Qufu Normal Univ, Inst Automat, Qufu, Shandong Provin, Peoples R China
来源
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2001年 / 31卷 / 02期
关键词
approximation problem; fuzzy logic controller (FLC); fuzzy set; universal approximator;
D O I
10.1109/3477.915352
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We first establish sufficient conditions for two classes of fuzzy logic controllers (FLCs) in [1] to approximate real polynomials to any degree of accuracy on a compact domain by using techniques different from those in [2]. Then, we give sufficient conditions for them to be universal approximators. Explicit formulas, which can be used to compute the number of fuzzy rules, are provided simultaneously. Compared with the results: in [2], the conditions here are less conservative since they require fewer fuzzy rules to approximate the same function, and the formulas derived here can be used to determine the number of fuzzy rules directly for multivariable polynomials. Sufficient conditions and explicit formulas to estimate the number of fuzzy rules are also provided when the functions to be approximated are not exactly known.
引用
收藏
页码:270 / 274
页数:5
相关论文
共 10 条
[1]   UNIVERSAL FUZZY CONTROLLERS [J].
BUCKLEY, JJ .
AUTOMATICA, 1992, 28 (06) :1245-1248
[2]   FUZZY-LOGIC CONTROLLERS ARE UNIVERSAL APPROXIMATORS [J].
CASTRO, JL .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1995, 25 (04) :629-635
[3]   Are fuzzy systems universal approximators? [J].
Klement, EP ;
Kóczy, LT ;
Moser, B .
INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 1999, 28 (2-3) :259-282
[4]  
KOSKO B, 1992, P IEEE INT C FUZZ SY, P1153
[5]   FUZZY BASIS FUNCTIONS, UNIVERSAL APPROXIMATION, AND ORTHOGONAL LEAST-SQUARES LEARNING [J].
WANG, LX ;
MENDEL, JM .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05) :807-814
[6]  
WANG LX, 1992, P IEEE INT C FUZZ SY, P1163, DOI DOI 10.1109/FUZZY.1992.258721
[7]   SUFFICIENT CONDITIONS ON GENERAL FUZZY-SYSTEMS AS FUNCTION APPROXIMATORS [J].
YING, H .
AUTOMATICA, 1994, 30 (03) :521-525
[8]   APPROXIMATION-THEORY OF FUZZY-SYSTEMS - MIMO CASE [J].
ZENG, XJ ;
SINGH, MG .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1995, 3 (02) :219-235
[9]   APPROXIMATION-THEORY OF FUZZY-SYSTEMS - SISO CASE [J].
ZENG, XJ ;
SINGH, MG .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1994, 2 (02) :162-176
[10]   A relationship between membership functions and approximation accuracy in fuzzy systems [J].
Zeng, XJ ;
Singh, MG .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1996, 26 (01) :176-180